per 1M tokens
DeepSeek: DeepSeek V3.1
deepseek/deepseek-chat-v3.1
DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...
Price
per 1M tokens
Providers
Each row is one seller. Prices are the published rate from that source. A dash means that source did not publish the amount. Sorted by a 3:1 blend of input and output.
| Provider | Tag | Quant | Input | Output | Context | Uptime | Status | Source |
|---|---|---|---|---|---|---|---|---|
| DeepInfra | deepinfra/fp4 | fp4 | $0.25/1M | $0.95/1M | 164K | 100% | Live | openrouter-endpoints |
| SiliconFlow | siliconflow/fp8 | fp8 | $0.27/1M | $1/1M | 164K | 100% | Live | openrouter-endpoints |
| CoreWeave | coreweave/fp8 | fp8 | $0.55/1M | $1.65/1M | 161K | 100% | Live | openrouter-endpoints |
| SambaNova | sambanova/fp8 | fp8 | $0.65/1M | $1.5/1M | 131K | 100% | Live | openrouter-endpoints |
| Mara | mara | — | $0.6/1M | $1.7/1M | 131K | 100% | Live | openrouter-endpoints |
Monthly bill
Token models use the token counts. Image, video, and audio models use units times the flat rate.
$1.20 at list price for this workload
Cache
per 1M tokens
Every rate
| Unit | Input | Output | Flat | Confidence |
|---|---|---|---|---|
| token | $0.25/1M | $0.95/1M | Not published— | official |
Price history
input or flat output
Daily snapshots
| UTC date | Unit | Input | Output | Flat |
|---|---|---|---|---|
| 2026-09-15 | token | $0.25 | $0.95 | Not published— |
| 2026-09-16 | token | $0.25 | $0.95 | Not published— |
| 2026-09-17 | token | $0.25 | $0.95 | Not published— |
| 2026-09-18 | token | $0.25 | $0.95 | Not published— |
| 2026-09-19 | token | $0.25 | $0.95 | Not published— |
| 2026-09-20 | token | $0.25 | $0.95 | Not published— |
| 2026-09-21 | token | $0.25 | $0.95 | Not published— |
| 2026-09-22 | token | $0.25 | $0.95 | Not published— |
| 2026-09-23 | token | $0.25 | $0.95 | Not published— |
| 2026-09-24 | token | $0.25 | $0.95 | Not published— |
| 2026-09-25 | token | $0.25 | $0.95 | Not published— |
| 2026-09-26 | token | $0.25 | $0.95 | Not published— |
| 2026-09-27 | token | $0.25 | $0.95 | Not published— |
| 2026-09-28 | token | $0.25 | $0.95 | Not published— |
| 2026-09-29 | token | $0.25 | $0.95 | Not published— |
| 2026-09-30 | token | $0.25 | $0.95 | Not published— |
| 2026-10-01 | token | $0.25 | $0.95 | Not published— |
| 2026-10-02 | token | $0.25 | $0.95 | Not published— |
| 2026-10-03 | token | $0.25 | $0.95 | Not published— |
| 2026-10-04 | token | $0.25 | $0.95 | Not published— |
| 2026-10-05 | token | $0.25 | $0.95 | Not published— |
| 2026-10-06 | token | $0.25 | $0.95 | Not published— |
| 2026-10-07 | token | $0.25 | $0.95 | Not published— |
| 2026-10-08 | token | $0.25 | $0.95 | Not published— |
| 2026-10-09 | token | $0.25 | $0.95 | Not published— |
| 2026-10-10 | token | $0.25 | $0.95 | Not published— |
| 2026-10-11 | token | $0.25 | $0.95 | Not published— |
| 2026-10-12 | token | $0.25 | $0.95 | Not published— |
| 2026-10-13 | token | $0.25 | $0.95 | Not published— |
| 2026-10-14 | token | $0.25 | $0.95 | Not published— |
| 2026-10-15 | token | $0.25 | $0.95 | Not published— |
| 2026-10-16 | token | $0.25 | $0.95 | Not published— |
| 2026-10-17 | token | $0.25 | $0.95 | Not published— |
| 2026-10-18 | token | $0.25 | $0.95 | Not published— |
| 2026-10-19 | token | $0.25 | $0.95 | Not published— |
| 2026-10-20 | token | $0.25 | $0.95 | Not published— |
| 2026-10-21 | token | $0.25 | $0.95 | Not published— |
| 2026-10-22 | token | $0.25 | $0.95 | Not published— |
| 2026-10-23 | token | $0.25 | $0.95 | Not published— |
| 2026-10-24 | token | $0.25 | $0.95 | Not published— |
| 2026-10-25 | token | $0.25 | $0.95 | Not published— |
| 2026-10-26 | token | $0.25 | $0.95 | Not published— |
| 2026-10-27 | token | $0.25 | $0.95 | Not published— |
| 2026-10-28 | token | $0.25 | $0.95 | Not published— |
| 2026-10-29 | token | $0.25 | $0.95 | Not published— |
| 2026-10-30 | token | $0.25 | $0.95 | Not published— |
Alternatives
- ByteDance Seed: Seed 1.6$0.25/1M · Compare
- ByteDance Seed: Seed-2.0-Lite$0.25/1M · Compare
- ByteDance/Seed-1.8$0.25/1M · Compare
- Claude 3 Haiku$0.25/1M · Compare
- deepseek-ai/DeepSeek-V3.1$0.25/1M · Compare
- Doubao Seed 1.6$0.25/1M · Compare
Parameters (19)
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Call this model
OpenRouter id deepseek/deepseek-chat-v3.1. InferenceList does not send the request.
curl
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"deepseek/deepseek-chat-v3.1","messages":[{"role":"user","content":"Hello"}]}'
JavaScript
await fetch("https://openrouter.ai/api/v1/chat/completions", {
method: "POST",
headers: {
Authorization: "Bearer " + process.env.OPENROUTER_API_KEY,
"Content-Type": "application/json",
},
body: JSON.stringify({
model: "deepseek/deepseek-chat-v3.1",
messages: [{ role: "user", content: "Hello" }],
}),
});
Python
import os, json, urllib.request
req = urllib.request.Request(
"https://openrouter.ai/api/v1/chat/completions",
data=json.dumps({"model": "deepseek/deepseek-chat-v3.1", "messages": [{"role": "user", "content": "Hello"}]}).encode(),
headers={"Authorization": "Bearer " + os.environ["OPENROUTER_API_KEY"], "Content-Type": "application/json"},
)
print(urllib.request.urlopen(req).read().decode())